Progressive depth growth builds large networks by starting with shallow models and inserting layers during training. Recent advances in large language models have renewed interest in this longstanding approach, demonstrating benefits for training efficiency and reasoning alongside changes in internal computations. Howe...
Amir Mohammad Karimi Mamaghan, Ferdinand Kapl, Andrea Dittadi et al.· 0 citations
Generating and editing presentation slides requires models to combine accurate text rendering, instruction following, visual grounding, aesthetic design, and precise editing within one canvas. Existing work covers only subsets of these capabilities and lacks large-scale slide-native supervision and diagnostic evaluatio...
Jia-Hao Wang, Xi-Yan Jiang, Chen-Yuan Wu et al.· 0 citations
Relational learning typically predicts from a database state, but decision making asks a different question: how will that state change under an action? In operational systems, the answer depends on system-specific dynamics that may not be visible in the database itself. We view each such system as a relational"world"a...
Attention sinks are usually studied after they have formed. We ask whether a measurable hidden-state change appears beforehand and whether changing that geometry alters what happens later. To remove network depth as a shortcut, we compare prompts in the same model and at the same layer. When sink timing varies across p...
Fan Yang, Yue Song· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Adversarial detection on evolving attributed graphs faces two challenges: fraud labels arrive late or not at all, and natural distributional drift erodes any trained decision boundary. Modern detectors can reach strong detection rates when labels are available and the distribution is stationary; sustaining that quality...
Recovering divergence-free velocity fields from sparse and corrupted observations requires reconciling physical consistency, expressive representations, and robustness to missing data. We introduce DFK-Former, a set-to-field transformer that reconstructs divergence-free velocity fields from sparse, noisy, and irregular...
Ramzi Idoughi, Radouan Boukharfane, Peter Wonka· 0 citations
Accurate long-term air quality forecasting is challenging due to long-range transport, meteorological variability, and nonlinear chemical reactions underlying secondary pollutant formation. Purely data-driven models often suffer from long-horizon drift and lack physical consistency, while existing physics-informed appr...
Kien Le Trung, Tung Kieu, Dinh Duc Nha Nguyen et al.· 0 citations
Existing human-centred XAI research predominantly evaluates explanations after they have been generated. However, this fails to provide actionable insights into improving accessibility. This study incorporates human-based feature understandability into feature selection to improve the generation of human-centred explan...
Nicola Rossberg, Bennett Kleinberg, Barry O'Sullivan et al.· 0 citations
A new framework of multimodal seizure classification integrating the heterogeneous EEG and iEEG recordings from different subjects and sources is presented, using the EEGNet-Vision Transformer as the feature extraction and classification network to learn the local discriminative patterns as well as global contextual in...
R. Sundaram, M. Jarwar, M. Uma et al.· 0 citations
Developing reliable predictive models for multi-physics systems often forces a compromise between computationally demanding physical simulators and data-hungry, opaque machine learning (ML) algorithms. While incorporating dimensional analysis into directed computation graphs offers a structurally sound alternative to e...
Akshay Dhalpe, Arnab Chattopadhyay, S. B. Balani et al.· 0 citations
Speculative Recursive Self-Improvement (SpecRSI) is introduced, which drafts executable successor agents before their predecessors are fully evaluated, while requiring complete verification before adoption.
Reinforcement learning (RL) can substantially improve the reasoning capabilities of large language models, but an effective training run requires considerable resources. Reusing the computation acquired through RL across models would extend the value of that training. We propose GrowRL, an RL method that organizes lear...
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
MIT News · Artificial Intelligence· news.mit.eduOct 27, 2026
Prabha Jha used her experience with MIT Open Learning’s program for senior executives to develop AI solutions for her employer, Verizon, and to write a book.
Assistant Professor Benjamin Lindquist studies how engineers deliberately injected randomness into early AI, giving rise to deep-learning models that sometimes hallucinate.
